if you look inside the code or run the script without any argument, it
tells you this:
-n Order of language model (default 3)
On 19/06/14 07:19, Rajkiran Rajkumar wrote:
In the baseline translation system, the command -
"~/irstlm/bin/build-lm.sh \
-i news-commentary-v8.fr-en.sb.en \
-t ./tmp -p -s improved-kneser-ney -o news-commentary-v8.fr-en.lm.en"
is used to create a "3-gram language model, removing singletons,
smoothing with improved Kneser-Ney, and adding sentence boundary
symbols" is what the tutorial says. How can I build a 2-gram language
model?
And, in general, which is more efficient for a bilingual corpus of
160,000 sentences? 2-gram or 3-gram?
Thanks in advance,
Rajkiran
College of Engineering Guindy, India
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support
